Research map / Bandits and online learning / Multi-armed bandits
Collaborative Pure Exploration in Kernel Bandit
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| Use globally optimal rather than locally optimal sample allocations (ablation) | CoKernelFC · Fixed-confidence simulations | sample complexity | Helped |
| Use globally optimal rather than locally optimal sample allocations (ablation) | CoKernelFB · Fixed-budget simulations | error probability | Helped |
| Collaborate using CoKernelFC instead of independently running single-agent methods | CoKernelFC · Fixed-confidence, identical tasks (rank(K_Z)=1) | sample complexity | Helped |
| Collaborate using CoKernelFC instead of independently running single-agent methods | CoKernelFC · Fixed-confidence, similar tasks (rank(K_Z) between 1 and V) | sample complexity | Helped |
| Collaborate using CoKernelFC instead of independently running single-agent methods | CoKernelFC · Fixed-confidence, unrelated tasks (rank(K_Z)=V) | sample complexity | No clear effect |
| Collaborate using CoKernelFB instead of independently running single-agent methods | CoKernelFB · Fixed-budget simulations | error probability | Helped |
| Decrease task similarity | CoKernelFB · Fixed-budget simulations | error probability | Hurt |
Closest papers by meaning
- Pure Exploration in Kernel and Neural Bandits (NeurIPS 2021 · similarity 0.90)
- Communication Efficient Distributed Learning for Kernelized Contextual Bandits (NeurIPS 2022 · similarity 0.89)
- Near-Optimal Collaborative Learning in Bandits (NeurIPS 2022 · similarity 0.88)
- FraPPE: Fast and Efficient Preference-Based Pure Exploration (NeurIPS 2025 · similarity 0.86)
- Infrequent Exploration in Linear Bandits (NeurIPS 2025 · similarity 0.86)
- Reward-Free Kernel-Based Reinforcement Learning (ICML 2024 · similarity 0.86)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.